net: ip_tunnel: fix mtu calculation for ETHER tunnel devices

Commit 28e104d00281 ("net: ip_tunnel: fix mtu calculation") removed
dev->hard_header_len subtraction when calculate MTU for tunnel devices
as there is an overhead for device that has header_ops.

But there are ETHER tunnel devices, like gre_tap or erspan, which don't
have header_ops but set dev->hard_header_len during setup. This makes
pkts greater than (MTU - ETH_HLEN) could not be xmited. Fix it by
subtracting the ETHER tunnel devices' dev->hard_header_len for MTU
calculation.

Fixes: 28e104d00281 ("net: ip_tunnel: fix mtu calculation")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index f6cc26d..0dca007 100644 (file)
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -317,7 +317,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
        }
 
        dev->needed_headroom = t_hlen + hlen;
-       mtu -= t_hlen;
+       mtu -= t_hlen + (dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0);
 
        if (mtu < IPV4_MIN_MTU)
                mtu = IPV4_MIN_MTU;
@@ -348,6 +348,9 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
        t_hlen = nt->hlen + sizeof(struct iphdr);
        dev->min_mtu = ETH_MIN_MTU;
        dev->max_mtu = IP_MAX_MTU - t_hlen;
+       if (dev->type == ARPHRD_ETHER)
+               dev->max_mtu -= dev->hard_header_len;
+
        ip_tunnel_add(itn, nt);
        return nt;
 
@@ -489,11 +492,14 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 
        tunnel_hlen = md ? tunnel_hlen : tunnel->hlen;
        pkt_size = skb->len - tunnel_hlen;
+       pkt_size -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0;
 
-       if (df)
+       if (df) {
                mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel_hlen);
-       else
+               mtu -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0;
+       } else {
                mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
+       }
 
        if (skb_valid_dst(skb))
                skb_dst_update_pmtu_no_confirm(skb, mtu);
@@ -972,6 +978,9 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
        int t_hlen = tunnel->hlen + sizeof(struct iphdr);
        int max_mtu = IP_MAX_MTU - t_hlen;
 
+       if (dev->type == ARPHRD_ETHER)
+               max_mtu -= dev->hard_header_len;
+
        if (new_mtu < ETH_MIN_MTU)
                return -EINVAL;
 
@@ -1149,6 +1158,9 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
        if (tb[IFLA_MTU]) {
                unsigned int max = IP_MAX_MTU - (nt->hlen + sizeof(struct iphdr));
 
+               if (dev->type == ARPHRD_ETHER)
+                       max -= dev->hard_header_len;
+
                mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, max);
        }